Difference between revisions of "3.4"

From Eigen
Jump to: navigation, search
Line 1: Line 1:
 
Raw dump of the main novelties and improvements that will be part of the 3.4 release compared to the 3.3 branch:
 
Raw dump of the main novelties and improvements that will be part of the 3.4 release compared to the 3.3 branch:
  
* Speed up evaluation of HouseholderSequence to a dense matrix, e.g.,<source lang="cpp">
+
* New features
 +
** New versatile API for sub-matrices, slices, and indexed views. Check the [http://eigen.tuxfamily.org/dox-devel/group__TutorialSlicingIndexing.html doc].
 +
** Reshaped views: [http://eigen.tuxfamily.org/dox-devel/group__TutorialReshape.html doc].
 +
* Performance optimizations
 +
** Vectorization of partial-reductions along outer-dimension, e.g.: colmajor.rowwise().mean()
 +
** Speed up evaluation of HouseholderSequence to a dense matrix, e.g.,<source lang="cpp">
 
MatrixXd Q = A.qr().householderQ();
 
MatrixXd Q = A.qr().householderQ();
 
</source>
 
</source>
* Versatile API for sub-matrices, slices, and indexed views.
+
* Hardware supports
* Reshaped
+
** Generalization of the CUDA support to CUDA/HIP for AMD GPUs.
* Vectorization of partial-reductions along outer-dimension, e.g.: colmajor.rowwise().mean()
+
** Add explicit support for MSA vectorization engine (MIPS).
* Generalization of the CUDA support to CUDA/HIP for AMD gpus.
+
** AVX512 is enabled by default when enabled on compiler side.
* Add MSA (MIPS) vectorization engine
+
* AVX512 is enabled by default when enabled on compiler side.
+

Revision as of 23:55, 10 November 2018

Raw dump of the main novelties and improvements that will be part of the 3.4 release compared to the 3.3 branch:

  • New features
    • New versatile API for sub-matrices, slices, and indexed views. Check the doc.
    • Reshaped views: doc.
  • Performance optimizations
    • Vectorization of partial-reductions along outer-dimension, e.g.: colmajor.rowwise().mean()
    • Speed up evaluation of HouseholderSequence to a dense matrix, e.g.,
      MatrixXd Q = A.qr().householderQ();
  • Hardware supports
    • Generalization of the CUDA support to CUDA/HIP for AMD GPUs.
    • Add explicit support for MSA vectorization engine (MIPS).
    • AVX512 is enabled by default when enabled on compiler side.